Evaluation Videos
Benchmarks, evals, and measuring AI system quality.
Evaluation separates AI systems that work in demos from systems that work in production. Benchmarks, LLM-as-judge pipelines, and domain-specific evals are how teams catch regressions and make model choices defensible — yet evaluation remains the most under-invested part of most AI stacks. The videos here cover benchmark design, eval tooling, and the observability practices that teams running LLMs in production rely on. This page aggregates Evaluation videos from every creator we track, so you can compare how official labs, educators, and practitioners approach the same subject. Videos are a starting point, not the whole picture. Below the video feed you will find hand-picked learning guides that explain the underlying concepts in depth, popular open-source GitHub repositories where the ideas live as code, and the AI tools most closely associated with Evaluation. We also surface the latest news coverage and research related to the topic, because a release video, its paper, and its press coverage each tell a different part of the story. Together they make this page a practical hub for going from "I watched a video about Evaluation" to actually understanding and building with it.